Active skeleton for non-rigid object detection

• Published in: 2009 IEEE 12th International Conference on Computer Vision pp. 575 - 582
• Main Authors: Xiang Bai, Xinggang Wang, Latecki, Longin Jan, Wenyu Liu, Zhuowen Tu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.09.2009
• Subjects: Automation; Educational institutions; Information science; Layout; Least squares approximation; Least squares methods; Light sources; Lighting; Object detection; Skeleton
• ISBN: 9781424444205; 1424444209
• ISSN: 1550-5499
• DOI: 10.1109/ICCV.2009.5459188

We present a shape-based algorithm for detecting and recognizing non-rigid objects from natural images. The existing literature in this domain often cannot model the objects very well. In this paper, we use the skeleton (medial axis) information to capture the main structure of an object, which has the particular advantage in modeling articulation and non-rigid deformation. Given a set of training samples, a tree-union structure is learned on the extracted skeletons to model the variation in configuration. Each branch on the skeleton is associated with a few part-based templates, modeling the object boundary information. We then apply sum-and-max algorithm to perform rapid object detection by matching the skeleton-based active template to the edge map extracted from a test image. The algorithm reports the detection result by a composition of the local maximum responses. Compared with the alternatives on this topic, our algorithm requires less training samples. It is simple, yet efficient and effective. We show encouraging results on two widely used benchmark image sets: the Weizmann horse dataset [7] and the ETHZ dataset [16].